Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4870
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks that are often used in citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contribución
    -0.43
     concentración
    -0.41
     colocación
    -0.39
     héroes
    -0.39
     autorización
    -0.37
     aseg
    -0.37
     réduit
    -0.36
     inhibit
    -0.36
     actúa
    -0.36
     consideración
    -0.36
    POSITIVE LOGITS
     Савезне
    0.75
     betweenstory
    0.67
     kasarigan
    0.67
    DrawerToggle
    0.65
     ivelany
    0.63
    contentLoaded
    0.62
     endforeach
    0.58
    oa̍t
    0.57
    Jeografia
    0.57
    sizeCache
    0.56
    Activations Density 0.027%

    No Known Activations